MBZUAI's IFM launches K2 Horizon: six fully open-source LLMs from 0.9B to 375B with full training data
YiMaTweets · x · 2026-09-04
The Institute of Foundation Models at MBZUAI has released K2 Horizon, six fully open-source LLMs spanning 0.9B to 375B parameters, billed as the largest fully open-source model launch in AI history.
- Full deployment coverage: six sizes (0.9B, 3.7B, 7.0B, 32B, 36B, 375B) targeting everything from smartwatches to enterprise data centers.
- Performance claims: SOTA or top-tier results per size class across reasoning, math, coding, and agentic tasks; the 375B flagship targets coding and agentic work against leading open-weight models.
- Radical openness: training code, data, and logs for the entire lifecycle are released, making results reproducible and extensible.
Models are live on Hugging Face alongside a launch page and tech blog.
Related event: MBZUAI's IFM Releases K2 Horizon: Six Fully Open Models from 0.9B to 375B(30 posts)→
More from Models
- Users want open-format export from Claude Docs as charts only save as images — BlackHC · 2026-10-20
- EMNLP study: LLM safety interventions drop up to 4.5x when distress is wrapped in delusion — MaartenSap · 2026-10-20
- Cybersecurity-focused VLM OrcaCyber-Nano-1.0 trends on Hugging Face — orcarouter · 2026-10-20
- 0.8B local model with 2,000 labels beats Jev's frontier API on banking data — kalyan_kpl · 2026-10-20
- New TTS benchmark tests 26 models across 30,564 requests: fastest at 46ms — mattturck · 2026-10-20
- Agents handle unreleased language Jai flawlessly, even compile-time execution — lucasmeijer · 2026-10-20